α_ SNFAQM: an active queue management mechanism using neurofuzzy prediction
Abstract
Active Queue Management (AQM) policies are mechanisms for congestion avoidance, which pro-actively drop packets in order to provide an early congestion notification to the sources. Random Early Detection (RED), the defacto standard and its different flavors have been proposed as simple solutions to the AQM problem. However, these approaches require manual tuning and fail to accurately capture variations in the input traffic, thereby resulting in unstable behavior. α_SNFAQM is a new AQM mechanism that uses a neurofuzzy prediction method (α_SNF) to capture traffic variation and accurately detect the future congestion. It distinguishes (i) severe congestion and (ii) light congestion. We compare the performance of α_SNFAQM with other AQM schemes like RED, PAQM and APACE in a bottleneck link. Simulation results have shown that α_SNFAQM outperforms other AQM schemes in stabilizing the instantaneous queue length, reducing packet loss ratio while keeping a high utilization of the link.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
These AQM schemes apply different supervised techniques for TSF and reinforcement-based methods for deducing the increment in the packet drop probability.
“these AQM schemes apply different supervised techniques for TSF [160, 179, 212, 498] and reinforcementbased methods for deducing the increment in the packet drop probability [298, 427, 428, 485, 499].”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [498]
α_SNFAQM achieves smaller and more stable queue length than PAQM and APACE, while providing comparable goodput.
“α_SNFAQM achieves smaller and more stable queue length than PAQM and APACE, while providing comparable goodput.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [498]
The α_SNF predictor slightly exceeds the accuracy of the NMLS-based predictor and incurs lower computational overhead.
“Simulations demonstrate that the α_SNF predictor slightly exceeds the accuracy of the NMLS-based predictor and incurs lower computational overhead.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [498]
α_SNFAQM produces more packet drops in order to notify congestion earlier.
“α_SNFAQM produce more packet drops in order to notify the congestion earlier.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [498]
Cites
Random early detection gateways for congestion avoidance
Floyd, S., & Jacobson, V. (1993) · IEEE/ACM Transactions on Networking · doi:10.1109/90.251892 · Cited by 6,290 · see citing works
Athuraliya, S., Low, S. H., Li, V. H., et al. (2001) · IEEE Network · doi:10.1109/65.923940 · Cited by 1,013 · see citing works
On designing improved controllers for AQM routers supporting TCP flows
Hollot, C. V., Misra, V., Towsley, D., & Gong, W. (2002) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infcom.2001.916670 · Cited by 964 · see citing works
Dynamics of random early detection
Lin, D., & Morris, R. (1997) · ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication (SIGCOMM) · doi:10.1145/263105.263154 · Cited by 795 · see citing works
Ott, T. J., Lakshman, T. V., & Wong, L. (1999) · doi:10.1109/infcom.1999.752153 · Cited by 678 · see citing works
The BLUE active queue management algorithms
Feng, W.-C., Shin, K. G., Kandlur, D. D., & Saha, D. (2002) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2002.801399 · Cited by 576 · see citing works
Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management
Kunniyur, S. S., & Srikant, R. (2001) · ACM SIGCOMM Computer Communication Review · doi:10.1145/964723.383069 · Cited by 133 · see citing works
PD-RED: to improve the performance of RED
Sun, J., Ko, K., Chen, G., et al. (2003) · IEEE Communications Letters · doi:10.1109/lcomm.2003.815653 · Cited by 124 · see citing works
Fair bandwidth sharing among adaptive and non-adaptive flows in the Internet
Anjum, F. M., & Tassiulas, L. (1999) · doi:10.1109/infcom.1999.752161 · Cited by 97 · see citing works
A state feedback control approach to stabilizing queues for ECN-enabled TCP connections
Gao, Y. X., & Hou, J. C. (2004) · doi:10.1109/infcom.2003.1209250 · Cited by 57 · see citing works
On exploiting traffic predictability in active queue management
Gao, Y., He, G., & Hou, J. C. (2003) · Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM) · doi:10.1109/infcom.2002.1019416 · Cited by 41 · see citing works
AFRED:an adaptive fuzzy-based control algorithm for active queue management
Wang, C., Li, B., Sohraby, K., et al. (2004) · doi:10.1109/lcn.2003.1243108 · Cited by 33 · see citing works
Congestion Control in IP Network
Feng, R. (2003) · Chinese Journal of Computers · Cited by 11 · see citing works
An adaptive prediction based approach for congestion estimation in active queue management (APACE)
Jain, A., Karandikar, A., & Verma, R. (2004) · IEEE Global Telecommunications Conference (GLOBECOM) · doi:10.1109/glocom.2003.1259009 · Cited by 10 · see citing works
PURPLE: Predictive active queue management utilizing congestion information
Pletka, R., Waldvogel, M., & Mannal, S. (2004) · doi:10.1109/lcn.2003.1243109 · Cited by 8 · see citing works
A new approach for fuzzy neural network weight initialization
Rouai, F. A., & Ahmed, M. B. (2002) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2001.939553 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., & Caicedo, O. M. (2018) · Journal of Internet Services and Applications · doi:10.1186/s13174-018-0087-2 · Cited by 1,036 · see citing works
Deep Blue: A Fuzzy Q-Learning Enhanced Active Queue Management Scheme
Masoumzadeh, S. S., Taghizadeh, G., Meshgi, K., & Shiry, S. (2009) · 2009 International Conference on Adaptive and Intelligent Systems · doi:10.1109/icais.2009.17 · Cited by 17 · see citing works
- Authors
- Zhani, M. F., Elbiaze, H., & Kamoun, F.
- Affiliations
- Université du Québec à Montréal (CA)
- Venue
- 2007 12th IEEE Symposium on Computers and Communications
- Publisher
- IEEE
- Published
- 2007-07
- Volume
- 26
- Pages
- 381-386
- ISSN
- 1530-1346 (ISSN-L)
- OpenAlex
- W1970813527
- Cited by
- 11
- References
- 16
- Citations by year
- 2023: 1 · 2021: 1 · 2018: 1 · 2012: 1
- FWCI
- 1.39
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Symposium on Computers and Communications (ISCC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
- Keywords
- active queue management, congestion avoidance, random early detection, packet dropping, traffic variability, packet loss rate, bottleneck link, link utilization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
